Thanks Richard, will commit the series if no comments for the second test only
patch in next 24 hours.
Pan
-----Original Message-----
From: Richard Biener <richard.guent...@gmail.com>
Sent: Tuesday, August 19, 2025 2:56 PM
To: Li, Pan2 <pan2...@intel.com>
Cc: gcc-patches@gcc.gnu.org; juzhe.zh...@rivai.ai; kito.ch...@gmail.com;
jeffreya...@gmail.com; rdapp....@gmail.com; Chen, Ken <ken.c...@intel.com>;
Liu, Hongtao <hongtao....@intel.com>
Subject: Re: [PATCH v2 1/2] Match: Add form 3 for unsigned SAT_MUL
On Thu, Aug 14, 2025 at 12:08 AM <pan2...@intel.com> wrote:
>
> From: Pan Li <pan2...@intel.com>
>
> This patch would like to try to match the the unsigned
> SAT_MUL form 3, aka below:
>
> #define DEF_SAT_U_MUL_FMT_3(NT, WT) \
> NT __attribute__((noinline)) \
> sat_u_mul_##NT##_from_##WT##_fmt_3 (NT a, NT b) \
> { \
> WT x = (WT)a * (WT)b; \
> if ((x >> sizeof(a) * 8) == 0) \
> return (NT)x; \
> else \
> return (NT)-1; \
> }
>
> While WT is T is uint16_t, uint32_t, uint64_t and uint128_t,
> and NT is is uint8_t, uint16_t, uint32_t and uint64_t.
OK.
Thanks,
Richard.
> gcc/ChangeLog:
>
> * match.pd: Add form 3 for unsigned SAT_MUL.
>
> Signed-off-by: Pan Li <pan2...@intel.com>
> ---
> gcc/match.pd | 27 ++++++++++++++++++++++++++-
> 1 file changed, 26 insertions(+), 1 deletion(-)
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 66e8a787449..b1d7a3a1b73 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3629,12 +3629,37 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> if (__builtin_mul_overflow (X, Y, &result))
> return -1;
> else
> - return -(T)overflow_p | result;
> + return result;
> }
> while T can be uint8_t, uint16_t, uint32_t and uint64_t. */
> (cond^ (ne (imagpart (IFN_MUL_OVERFLOW:c@2 @0 @1)) integer_zerop)
> integer_minus_onep (realpart @2))
> (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_mul @0 @1)
> + /* SAT_U_MUL (X, Y) = {
> + WT x = (WT)a * (WT)b;
> + if ((x >> sizeof(a) * 8) == 0)
> + return (T)x;
> + else
> + return (T)-1;
> + }
> + while WT is uint128_t, T is uint8_t, uint16_t, uint32_t or uint64_t.
> */
> + (convert (cond^ (eq (rshift (mult:c@3 (convert @0) (convert @1))
> + INTEGER_CST@2)
> + integer_zerop)
> + @3 INTEGER_CST@4))
> + (if (types_match (type, @0, @1))
> + (with
> + {
> + unsigned prec = TYPE_PRECISION (type);
> + unsigned widen_prec = TYPE_PRECISION (TREE_TYPE (@3));
> + wide_int c4 = wi::to_wide (@4);
> + wide_int max = wi::mask (prec, false, widen_prec);
> + bool c4_is_max_p = wi::eq_p (c4, max);
> + unsigned c2 = tree_to_uhwi (@2);
> + bool c2_is_type_precision_p = c2 == prec;
> + }
> + (if (widen_prec > prec && c2_is_type_precision_p && c4_is_max_p)))))
> )
>
> /* The boundary condition for case 10: IMM = 1:
> --
> 2.43.0
>
